dev-release

dev-release is a skill for Claude Code from RelationalAI/rai-agent-skills. It costs 47 tokens per session (2,187 once invoked), scanned A, original, Apache-2.0.

A local release procedure for the rai-agent-skills plugin that updates its version, records the changes in Git, and creates a local tag. A Git tag is a named marker for a specific version of the code.

In plain words
What is it for?
Use it when cutting a release of the canonical RelationalAI/rai-agent-skills repository from its main branch, provided the working tree is ready and the required GitHub tools are available.
Why use it?
It keeps the plugin’s version records synchronized and avoids users receiving an old cached copy after code changes. Publishing and pushing remain separate steps for human review.

Skill for Claude Code

Written for Claude Code: Claude Code plugin machinery. Also seen: mentions Claude Code; mentions Codex.

Good fit Use it when cutting a release of the canonical RelationalAI/rai-agent-skills repository from its main branch, provided the working tree is ready and the required GitHub tools are available.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/relationalai/rai-agent-skills/dev-release
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add RelationalAI/rai-agent-skills --skill dev-release
Clone the repo
git clone --depth 1 https://github.com/RelationalAI/rai-agent-skills

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for dev-release

README.md
[![agentmods](https://agentmods.dev/badge/skills/relationalai/rai-agent-skills/dev-release.svg)](https://agentmods.dev/skills/relationalai/rai-agent-skills/dev-release)
Your own site
<a href="https://agentmods.dev/skills/relationalai/rai-agent-skills/dev-release"><img src="https://agentmods.dev/badge/skills/relationalai/rai-agent-skills/dev-release.svg" alt="Measured on agentmods" height="20"></a>
Per session 47 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,187 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00047 $0.02187
Opus 5 $0.00023 $0.01094
Sonnet 5 $0.00009 $0.00437
Haiku 4.5 $0.00005 $0.00219

Measured 8d ago against content hash 13efda1a993a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

dev-release scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 8d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/release.sh), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

contrib/dev-release/SKILL.md · 225 lines

How it starts

The opening of the file, as written. The whole thing — 225 lines — stays where its author put it; the contents beside it link to each section on GitHub.

RAI Release: Bump + Tag (local) → Push + Publish (human-gated)

Claude Code treats plugin.json version as the plugin cache key — if you ship code changes without bumping, end users silently keep the cached copy. All three manifests that carry the plugin version must stay in sync.

The helper script handles the mechanical, local parts (bump manifests, commit, create the tag). It deliberately does not push or publish — those steps happen under human review via the publishing procedure, so the releaser can review repo state and shape release notes before anything user-visible lands on origin.

Assumptions

This workflow targets the canonical repo and assumes:

  • You're on main in a clone of RelationalAI/rai-agent-skills, with origin pointing at it.
  • You have push access to main and permission to create tags + releases on origin. Only RAI maintainers do — if git push origin prompts for credentials or gh release create 403s, stop.
  • gh is installed and authenticated.
  • Working tree has no uncommitted tracked changes (untracked files are fine).

Running against a fork or a feature branch will put the release on the wrong branch/repo. Don't do it.

Files carrying the plugin version

The plugin version lives in exactly three files — the official plugin metadata for each supported host (Claude Code, Codex, Cursor). Keep them identical. Any other version field in the repo is out of scope for this skill.

  • plugins/rai/.claude-plugin/plugin.json
  • plugins/rai/.codex-plugin/plugin.json
  • plugins/rai/.cursor-plugin/plugin.json

Adding or removing a plugin host (e.g. Gemini, a new marketplace) means this list changes. When that happens, update both:

  • This skill — the list above, the count in the intro, the wc -l expected value in the Manual path verification step, and the OLD/NEW bump loop.
  • The script — the FILES array in contrib/dev-release/scripts/release.sh.

A release run with an out-of-date FILES array will silently skip the new manifest.

Read the full file on GitHub · 225 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 8d ago First seen · 225 lines · 47 tokens per session scan A 13efda1a993a

Subscribe to this mod's changes

dev-release is a skill published in the GitHub repository RelationalAI/rai-agent-skills (4 stars, last pushed 6d ago), licensed Apache-2.0. It adds 47 tokens to every session and 2,187 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.